Veit Hagenmeyer

The paper proposes RTS-ABAC, a novel real-time server-aided Attribute-Based Access Control mechanism designed to secure time-critical communications in substation automation systems, achieving low-latency protection even for retrofitting existing infrastructure.

The paper introduces CritBench, a novel framework to evaluate LLM cybersecurity capabilities specifically within IEC 61850 Digital Substation Operational Technology (OT) environments, finding that while models understand the standards, they struggle with dynamic, stateful system manipulation.

The paper introduces CyberCertBench, a new benchmark suite for evaluating LLMs against industry cybersecurity certifications, finding that while frontier models perform well on general knowledge, their accuracy drops when specialized or vendor-specific standards are required.

This paper proposes an Explainable Deep Reinforcement Learning (XRL) framework to optimize energy management in complex buildings, demonstrating that on-policy algorithms provide superior cost reduction while offering transparent decision-making insights.

FlowGuard introduces an identity-independent defense using flow matching to detect data-free model stealing attacks by identifying synthetic queries as out-of-distribution based on their lower-dimensional manifold structure.

This paper demonstrates that current AI model extraction defenses, which assume attacks come from single sources, are easily bypassed by coordinated, distributed threat actors.